Conditional Evidence Reconstruction and Decomposition for Interpretable Multimodal Diagnosis

ArXi:2604.17030v1 Announce Type: new Neurobiological and neurodegenerative diseases are inherently multifactorial, arising from coupled influences spanning genetic susceptibility, brain alterations, and environmental and behavioral factors. Multimodal modeling has therefore been increasingly adopted for disease diagnosis by integrating complementary evidence across data sources. However, in both large-scale cohorts and real-world clinical workflows, modality coverage is often incomplete, making many multimodal models brittle when one or modalities are unavailable.